Model comparison
DeepSeek V4.1 Flash vs GPT-4.5
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 37.2 on the Noometry Index.
Last verified . 21 shared benchmarks.
DeepSeekSummary
- They share 21 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 10 categories and GPT-4.5 in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 50.2 to 13.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 37.8% for GPT-4.5.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | GPT-4.5 | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 52.8 | 37.2 |
| Released | 2026-09-09 | 2025-02-27 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 37 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), GPT-4.5: 42.2 (#109)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| LMArena Coding | 1506 | 1396 |
| Aider Polyglot | — | 44.9% |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| WeirdML | — | 39.4% |
| LiveBench Coding | — | 75.2% |
| ALE-Bench | 1,092 | — |
Agentic & Tool Use DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 31.2 (#69), GPT-4.5: 27.9 (#97)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| APEX-Agents | 39.5% | — |
| Cybench | — | 17.5% |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), GPT-4.5: 13.9 (#330)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1403 |
| Epoch Capabilities Index | 154.9 | 136.74 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | — | 10.3% |
| CritPt | 14.3% | — |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LiveBench Data Analysis | — | 64.3% |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), GPT-4.5: 32.6 (#211)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 37.8% |
| LMArena Math | 1477 | 1412 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| ProofBench | 54% | — |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), GPT-4.5: 32.5 (#211)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 89.8% | 68.7% |
| LMArena Expert | 1506 | 1394 |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |
Multimodal DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 39.1 (#61), GPT-4.5: 37.6 (#71)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1277 | 1195 |
| VPCT | — | 45% |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), GPT-4.5: 52.5 (#83)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1448 | 1413 |
| LMArena Chinese | 1497 | 1421 |
| LMArena French | 1452 | 1418 |
| LMArena German | 1484 | 1457 |
| LMArena Japanese | 1412 | 1416 |
| LMArena Korean | 1452 | 1392 |
| LMArena Russian | 1471 | 1419 |
| LMArena Spanish | 1459 | — |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), GPT-4.5: 72.6 (#134)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1474 | 1404 |
| LiveBench Instruction Following | — | 72.3% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), GPT-4.5: 40.4 (#155)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1475 | 1406 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), GPT-4.5: 56.9 (#134)
| Benchmark | DeepSeek V4.1 Flash | GPT-4.5 |
|---|---|---|
| LMArena Text | 1462 | 1417 |
| LMArena Creative Writing | 1435 | 1394 |
| EQ-Bench Creative Writing | 1540 | 1258 |
| LMArena Multi-Turn | 1457 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| LiveBench Language | — | 61.5% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than GPT-4.5?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 37.2 on the Noometry Index.
Is DeepSeek V4.1 Flash or GPT-4.5 better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 42.2 in the Noometry coding category.
How many benchmarks do DeepSeek V4.1 Flash and GPT-4.5 share?
21 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and GPT-4.5 has 42.